Explore chapters and articles related to this topic
Behavior Modeling of Human Objects in Multimedia Content
Published in Frank Y. Shih, Multimedia Security, 2017
A particle filter is a Monte Carlo method for nonlinear, non-Gaussian models, which approximates the continuous probability density function by using a large number of samples. In the HGPDM framework, a histogram was used as appearance modeling for its simplicity and efficiency. The red, green, blue (RGB) histogram of the template and the image region under consideration are obtained, respectively. The likelihood P(Zt|kt,Y^t) is defined to be proportional to the similarity between the histogram of the template and the candidate, and is measured by the Bhattacharya distance.
Monitoring Health and Wellness Indicators for Aging in Place
Published in Mohammad Ilyas, Sami S. Alwakeel, Mohammed M. Alwakeel, el-Hadi M. Aggoune, Sensor Networks for Sustainable Development, 2017
Kevin Bing-Yung Wong, Tongda Zhang, Hamid Aghajan
The general approach to applying a particle filter on the CASAS dataset was based largely on the approach developed by Thrun et al. [35]. However, many assumptions and simplifications had to be made in order to define the probability distributions required to update the particle filter. A particle filter uses an iterative process to update a set of particles that represent samples of the estimated user position. These particles are represented by the set ξt, which encodes the positions of the particles: χt:=xt[1],xt[2],…,xt[N]
Prognostic modelling for industrial asset health management
Published in Safety and Reliability, 2022
Neda Gorjian Jolfaei, Raufdeen Rameezdeen, Nima Gorjian, Bo Jin, Christopher W. K. Chow
A particle filter is a method to use a set of samples to represent the posterior distribution of the stochastic process given noisy and/or partial observations where the process is non-Gaussian. Yan et al. (2021) proposed a model to estimate machinery degradation based on failure processes subject to the gradual degradation and random shocks using a particle filter model. Chang and Fang (2019) used the particle filter and vector machine methods to model the degradation process and calculate uncertainties of lithium-ion batteries’ RUL prediction. A joint particle filter and Expectation-Maximisation (EM) algorithms was proposed by Wang et al. (2019) to model machinery condition prognosis due to the stochastic behaviour of machinery defects and failures under variable operating conditions.
Stream travel time prediction using particle filtering approach
Published in Transportation Letters, 2018
B. Dhivyabharathi, E. S. Hima, L. Vanajakshi
Most of the recursive estimation tools like Kalman filter and Extended Kalman filter hold the assumption of Gaussian distribution for noise. Particle Filter is one technique which can be applied to any general non-linear or non-Gaussian problem. The main advantage of Particle Filter is that it does not require the process and sensor noise to be Gaussian distributed. Also, the use of particle filtering in the field of Traffic Engineering for traffic state prediction is very limited. Hence, the current study explores the use and applicability of Particle filter for travel time prediction problem.
Spatial concept-based navigation with human speech instructions via probabilistic inference on Bayesian generative model
Published in Advanced Robotics, 2020
Akira Taniguchi, Yoshinobu Hagiwara, Tadahiro Taniguchi, Tetsunari Inamura
The online learning algorithm introduces sequential equation updates to estimate the parameters of the spatial concepts into the formulation of a Rao-Blackwellized particle filter [26] in the FastSLAM 2.0 [27] and its grid-based SLAM [28]. The particle filter is advantageous in that parallel processing can be easily applied because particles can be calculated independently. Theoretically, other particle filter-based SLAMs besides FastSLAM 2.0 can also be used.